Robot Navigation in Risky, Crowded Environments: Understanding Human Preferences

TL;DR

This study explores human path choices in risky, crowded environments to inform the development of explainable AI for robot navigation, revealing diverse preferences and the superiority of CPT in modeling decision-making.

Contribution

It introduces a novel COVID-19 grocery shopping scenario for studying human navigation choices and evaluates risk models, highlighting CPT's effectiveness in capturing human decision behavior.

Findings

Participants show diverse path preferences from risky to safe.

CPT models human decision-making more accurately than CVaR and ER.

Self-assessed risk does not correlate with actual path choices.

Abstract

Risky and crowded environments (RCE) contain abstract sources of risk and uncertainty, which are perceived differently by humans, leading to a variety of behaviors. Thus, robots deployed in RCEs, need to exhibit diverse perception and planning capabilities in order to interpret other human agents' behavior and act accordingly in such environments. To understand this problem domain, we conducted a study to explore human path choices in RCEs, enabling better robotic navigational explainable AI (XAI) designs. We created a novel COVID-19 pandemic grocery shopping scenario which had time-risk tradeoffs, and acquired users' path preferences. We found that participants showcase a variety of path preferences: from risky and urgent to safe and relaxed. To model users' decision making, we evaluated three popular risk models (Cumulative Prospect Theory (CPT), Conditional Value at Risk (CVAR), and Expected Risk (ER). We found that CPT captured people's decision making more accurately than CVaR and ER, corroborating theoretical results that CPT is more expressive and inclusive than CVaR and ER. We also found that people's self assessments of risk and time-urgency do not correlate with their path preferences in RCEs. Finally, we conducted thematic analysis of open-ended questions, providing crucial design insights for robots is RCE. Thus, through this study, we provide novel and critical insights about human behavior and perception to help design better navigational explainable AI (XAI) in RCEs.